debug-fe-be-integration

Pass

Audited by Gen Agent Trust Hub on Nov 1, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted data from external sources and uses it to perform sensitive operations, creating an attack surface for indirect prompt injection.
  • Ingestion points: The skill reads error data from Sentry using sentry:search_issues and monitors live terminal output from backend logs (terminals/*.txt).
  • Boundary markers: The instructions do not specify any boundary markers or delimiters to separate ingested log content from the agent's instructions, nor do they include warnings to ignore instructions embedded within the logs.
  • Capability inventory: The skill possesses significant capabilities, including reading local source code via Grep, performing semantic searches across the project, and executing SQL queries via supabase:execute_sql based on findings from the logs.
  • Sanitization: There is no evidence of sanitization, escaping, or validation of the data extracted from logs before it is interpolated into tool calls (e.g., using log-derived table names or conditions in SQL queries).
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 1, 2026, 08:17 AM